尿检
口译(哲学)
医学
透视图(图形)
医学物理学
自然语言处理
计算机科学
重症监护医学
心理学
风险评估
肾
梅德林
人工智能
肾脏疾病
工作(物理)
间隙
英语
作者
Tao Liu,Xinglun Qi,Mohui Guo,Xianfei Ye,Lina Fan,De Yang
标识
DOI:10.1515/cclm-2026-0435
摘要
OBJECTIVES: Large language models (LLMs) show promise for interpreting laboratory reports, yet real-world validation remains limited. This study evaluated five advanced LLMs in interpreting urinalysis reports for kidney diseases using real-world clinical data, providing empirical evidence for the utility of LLM-assisted result interpretation. METHODS: We retrospectively collected 120 urinalysis reports from patients with primary glomerular diseases and secondary nephropathies. The testing platforms included the Sysmex UF5000 and Mindray EU8600. Five LLMs (ChatGPT-5, Claude-4.5, Gemini-2.5, DeepSeek-V3.1, Qwen-3) were tasked with interpreting reports across five functional dimensions. Four certified laboratory technologists and four licensed physicians evaluated outputs using a 5-point Likert scale across six quality dimensions. Statistical analyses employed Friedman and Wilcoxon signed-rank tests. RESULTS: All five LLMs demonstrated clinical utility in interpreting urinalysis reports. Proprietary LLMs achieved higher overall scores (Claude-4.5: 4.78 ± 0.47; ChatGPT-5: 4.73 ± 0.50; Gemini-2.5: 4.69 ± 0.54) compared to open-source LLMs (DeepSeek-V3.1: 4.58 ± 0.66; Qwen-3: 4.57 ± 0.69). Across functional dimensions, the models performed proficiently in identifying abnormal parameters and analyzing their correlations, but suboptimally in interpreting instrument flags. Instrument-dependent variability was observed (Sysmex vs. Mindray, p<0.001). In quality assessments, Claude-4.5 exhibited the best overall performance, ChatGPT-5 excelled in accuracy and clarity, and Gemini-2.5 demonstrated strong practicality. Regarding safety, Claude-4.5 exhibited the lowest hallucination rate (7.5 %). Common hallucinations included misinterpretation, definition errors, and over-interpretation. CONCLUSIONS: LLMs demonstrate significant capability in urinalysis interpretation, though proprietary models currently excel in reasoning and hallucination resistance. Instrument-specific flag interpretation and hallucination mitigation remain critical challenges requiring Retrieval-Augmented Generation (RAG) integration and human oversight.
科研通智能强力驱动
Strongly Powered by AbleSci AI